• 9 Posts
  • 2.2K Comments
Joined 2 years ago
cake
Cake day: April 30th, 2024

help-circle





  • I was just moved to Italy. I knew no one and I had to do some history assignment for Uni. I went to the city archive looking for some documentation and I was incredibly lost.

    Some middle age man approached me and starting helping me around. He talked with everybody there and they all respected them. He was really nice to me all the time. I got into the archive and got everything I wanted. But I was more creepied out each minute. The guy had starting talking about how spaniards(me) and italians needs to be friends because our shared history of friendship with Franco and Mussolini. At the end he asked for my number, he really looked like he was trying to recruit me. I gave him a fake one and moved away. Never got near that location again in all the the time I spent in the city.







  • I 100% understand and support why the moved away from google.

    And Motorola was a good choice. But they really should have supported some budget phones.

    A pixel series a could easily be found for under 500€ new. These flagship motorola phones are all way over 1000€.

    And the developer clearly said they had currently no intention to support cheaper motorola phones. Among other things because Motorola won’t offer 7 year updates for anything but these flagships.

    So, I get it. But let’s face it that people on a budget will keep using pixels for GOS while they are maintained.



  • I’m not upset.

    As said I have use it. Both for image generation and llm for text generation. But knowing what they can and cannot do.

    I mostly use it for roleplay. And generating images of places and characters on the go is fun and easy. But it’s not a tool that allow for a very high degree of creativity. Neither have the ability to put the “image” that someone has in their head onto canvas.


  • I have tried.

    I spent several days on a comfyui workflow.

    Using Anima as base model, with controlUI, trying loras, IMG2IMG with flux.

    It’s very clear that the generation is limited to a dataset.

    Even more clear when you use SDXL that basically works by tags.

    But even with models which process natural languages you see the limitations imposed by the training data.

    If you want to make a generic image that’s been done 10000 times it’s very easy. But if you want to do something very specific that the thing have not been trained to do… you are not going to make it. Unless you literally paint want you want and train a lora with it, which kind of defeats the purpose.